diff --git a/pygments/lexers/html.py b/pygments/lexers/html.py
index 277148082f..b711e2feb2 100644
--- a/pygments/lexers/html.py
+++ b/pygments/lexers/html.py
@@ -77,12 +77,24 @@ class HtmlLexer(RegexLexer):
bygroups(Punctuation, Text, Punctuation, Text, Name.Tag, Text,
Punctuation), '#pop'),
(r'.+?(?=<\s*/\s*script\s*>)', using(JavascriptLexer)),
+ # fallback cases for when there is no closing script tag
+ # first look for newline and then go back into root state
+ # if that fails just read the rest of the file
+ # this is similar to the error handling logic in lexer.py
+ ('.+?\n', using(JavascriptLexer), '#pop'),
+ (r'.+', using(JavascriptLexer), '#pop'),
],
'style-content': [
(r'(<)(\s*)(/)(\s*)(style)(\s*)(>)',
bygroups(Punctuation, Text, Punctuation, Text, Name.Tag, Text,
Punctuation),'#pop'),
(r'.+?(?=<\s*/\s*style\s*>)', using(CssLexer)),
+ # fallback cases for when there is no closing style tag
+ # first look for newline and then go back into root state
+ # if that fails just read the rest of the file
+ # this is similar to the error handling logic in lexer.py
+ ('.+?\n', using(JavascriptLexer), '#pop'),
+ (r'.+', using(JavascriptLexer), '#pop'),
],
'attr': [
('".*?"', String, '#pop'),
diff --git a/tests/test_html_lexer.py b/tests/test_html_lexer.py
new file mode 100644
index 0000000000..fe3ddf593e
--- /dev/null
+++ b/tests/test_html_lexer.py
@@ -0,0 +1,80 @@
+# -*- coding: utf-8 -*-
+"""
+ HTML Lexer Tests
+ ~~~~~~~~~~~~~~~~
+
+ :copyright: Copyright 2020-2020 by the Pygments team, see AUTHORS.
+ :license: BSD, see LICENSE for details.
+"""
+
+import time
+
+import pytest
+
+from pygments.lexers.html import HtmlLexer
+from pygments.token import Token
+
+@pytest.fixture(scope='module')
+def lexer_html():
+ yield HtmlLexer()
+
+def test_simple_html(lexer_html):
+ """ extremely basic happy-path case
+
+ more tests are in test_examplefiles """
+
+ fragment = "\n\t\n\t\thello world\n\t\n"
+ tokens = list(lexer_html.get_tokens(fragment))
+ assert all(x[1] != Token.Error for x in tokens)
+
+def test_happy_javascript_fragment(lexer_html):
+ """ valid, even long Javascript fragments should still get parsed ok """
+
+ fragment = ""
+ start_time = time.time()
+ tokens = list(lexer_html.get_tokens(fragment))
+ assert all(x[1] != Token.Error for x in tokens)
+ assert time.time() - start_time < 1, 'The HTML lexer might have an expensive happy-path script case'
+
+def test_happy_css_fragment(lexer_html):
+ """ valid, even long CSS fragments should still get parsed ok """
+
+ fragment = ""
+ start_time = time.time()
+ tokens = list(lexer_html.get_tokens(fragment))
+ assert all(x[1] != Token.Error for x in tokens)
+ assert time.time() - start_time < 1, 'The HTML lexer might have an expensive happy-path style case'
+
+def test_long_unclosed_javascript_fragment(lexer_html):
+ """ unclosed, long Javascript fragments should parse quickly """
+
+ fragment = "